{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:35XN2LAYDRBSJISCOHI3DLDBFB","short_pith_number":"pith:35XN2LAY","schema_version":"1.0","canonical_sha256":"df6edd2c181c4324a24271d1b1ac61284a1b58aece2d4a5384ff0b29289b3443","source":{"kind":"arxiv","id":"2606.24391","version":1},"attestation_state":"computed","paper":{"title":"Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Arnaud Ricci","submitted_at":"2026-06-23T10:25:31Z","abstract_excerpt":"We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy the enemy base. Three stressors are deliberate: fog of war, full diplomacy (messages, ceasefires, ultimatums; uranium kept secret), and a reliability dimension where every turn must follow a strict JSON schema and an illegal action is silently discarded. The engine is private and each match uses a fresh random map seed and opponent, mitigating the data contamination that affects public benchmarks. Models receive a (near) rule-only prompt with no build-order advice (two tactical seed phrases"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.24391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T10:25:31Z","cross_cats_sorted":["cs.CL","cs.GT","cs.MA"],"title_canon_sha256":"324827dc1ebe03119e978c9c7b56e956f9d062b7e0555be6220f6fcc1bba9fcb","abstract_canon_sha256":"fcf557645e607cd91f470a2a83e19673f474f57c1f2d5d54b6f2e2011225995b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:29.390134Z","signature_b64":"LLkZ1ox+Glz8TxUWyYefOokUxAkFBKZ3OBvKeK47ZYI8wuwczn5GvnQw3H6GUkYPD4bFWi7SITepBCZxt0n2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df6edd2c181c4324a24271d1b1ac61284a1b58aece2d4a5384ff0b29289b3443","last_reissued_at":"2026-06-24T01:15:29.389756Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:29.389756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Arnaud Ricci","submitted_at":"2026-06-23T10:25:31Z","abstract_excerpt":"We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy the enemy base. Three stressors are deliberate: fog of war, full diplomacy (messages, ceasefires, ultimatums; uranium kept secret), and a reliability dimension where every turn must follow a strict JSON schema and an illegal action is silently discarded. The engine is private and each match uses a fresh random map seed and opponent, mitigating the data contamination that affects public benchmarks. Models receive a (near) rule-only prompt with no build-order advice (two tactical seed phrases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24391","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.24391/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24391","created_at":"2026-06-24T01:15:29.389805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24391v1","created_at":"2026-06-24T01:15:29.389805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24391","created_at":"2026-06-24T01:15:29.389805+00:00"},{"alias_kind":"pith_short_12","alias_value":"35XN2LAYDRBS","created_at":"2026-06-24T01:15:29.389805+00:00"},{"alias_kind":"pith_short_16","alias_value":"35XN2LAYDRBSJISC","created_at":"2026-06-24T01:15:29.389805+00:00"},{"alias_kind":"pith_short_8","alias_value":"35XN2LAY","created_at":"2026-06-24T01:15:29.389805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB","json":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB.json","graph_json":"https://pith.science/api/pith-number/35XN2LAYDRBSJISCOHI3DLDBFB/graph.json","events_json":"https://pith.science/api/pith-number/35XN2LAYDRBSJISCOHI3DLDBFB/events.json","paper":"https://pith.science/paper/35XN2LAY"},"agent_actions":{"view_html":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB","download_json":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB.json","view_paper":"https://pith.science/paper/35XN2LAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24391&json=true","fetch_graph":"https://pith.science/api/pith-number/35XN2LAYDRBSJISCOHI3DLDBFB/graph.json","fetch_events":"https://pith.science/api/pith-number/35XN2LAYDRBSJISCOHI3DLDBFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB/action/storage_attestation","attest_author":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB/action/author_attestation","sign_citation":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB/action/citation_signature","submit_replication":"https://pith.science/pith/35XN2LAYDRBSJISCOHI3DLDBFB/action/replication_record"}},"created_at":"2026-06-24T01:15:29.389805+00:00","updated_at":"2026-06-24T01:15:29.389805+00:00"}